Learning Better Features for Face Detection with Feature Fusion and Segmentation Supervision

by   Wanxin Tian, et al.

The performance of face detectors has been largely improved with the development of convolutional neural network. However, it remains challenging for face detectors to detect tiny, occluded or blurry faces. Besides, most face detectors can't locate face's position precisely and can't achieve high Intersection-over-Union (IoU) scores. We assume that problems inside are inadequate use of supervision information and imbalance between semantics and details at all level feature maps in CNN even with Feature Pyramid Networks (FPN). In this paper, we present a novel single-shot face detection network, named DF^2S^2 (Detection with Feature Fusion and Segmentation Supervision), which introduces a more effective feature fusion pyramid and a more efficient segmentation branch on ResNet-50 to handle mentioned problems. Specifically, inspired by FPN and SENet, we apply semantic information from higher-level feature maps as contextual cues to augment low-level feature maps via a spatial and channel-wise attention style, preventing details from being covered by too much semantics and making semantics and details complement each other. We further propose a semantic segmentation branch to best utilize detection supervision information meanwhile applying attention mechanism in a self-supervised manner. The segmentation branch is supervised by weak segmentation ground-truth (no extra annotation is required) in a hierarchical manner, deprecated in the inference time so it wouldn't compromise the inference speed. We evaluate our model on WIDER FACE dataset and achieved state-of-art results.


page 2

page 3


Feature Agglomeration Networks for Single Stage Face Detection

Recent years have witnessed promising results of face detection using de...

ScarfNet: Multi-scale Features with Deeply Fused and Redistributed Semantics for Enhanced Object Detection

Convolutional neural network (CNN) has led to significant progress in ob...

Single-Shot Object Detection with Enriched Semantics

We propose a novel single shot object detection network named Detection ...

Deep Co-supervision and Attention Fusion Strategy for Automatic COVID-19 Lung Infection Segmentation on CT Images

Due to the irregular shapes,various sizes and indistinguishable boundari...

PyramidBox: A Context-assisted Single Shot Face Detector

Face detection has been well studied for many years and one of the remai...

PIDNet: A Real-time Semantic Segmentation Network Inspired from PID Controller

Two-branch network architecture has shown its efficiency and effectivene...

SymmetricNet: A mesoscale eddy detection method based on multivariate fusion data

Mesoscale eddies play a significant role in marine energy transport, mar...

Please sign up or login with your details

Forgot password? Click here to reset